Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3497 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.2729. Min Range: -7.2729
Max Act: 7.2729. Min Act: -0.1700
Data Index: 7835571 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2729. Min Range: -7.2729
Max Act: 7.2417. Min Act: -0.1700
Data Index: 6411130 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2729. Min Range: -7.2729
Max Act: 7.1167. Min Act: -0.1700
Data Index: 5586680 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2729. Min Range: -7.2729
Max Act: 7.0542. Min Act: -0.1700
Data Index: 5513899 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2729. Min Range: -7.2729
Max Act: 6.9917. Min Act: -0.1700
Data Index: 562345 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2729. Min Range: -7.2729
Max Act: 6.9917. Min Act: -0.1700
Data Index: 7189563 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2729. Min Range: -7.2729
Max Act: 6.9292. Min Act: -0.1700
Data Index: 2638141 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2729. Min Range: -7.2729
Max Act: 6.9292. Min Act: -0.1700
Data Index: 2317455 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2729. Min Range: -7.2729
Max Act: 6.8979. Min Act: -0.1700
Data Index: 2206166 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2729. Min Range: -7.2729
Max Act: 6.9292. Min Act: -0.1700
Data Index: 142083 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2729. Min Range: -7.2729
Max Act: 6.8667. Min Act: -0.1700
Data Index: 3970179 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2729. Min Range: -7.2729
Max Act: 6.9292. Min Act: -0.1700
Data Index: 1292376 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2729. Min Range: -7.2729
Max Act: 6.8979. Min Act: -0.1700
Data Index: 466770 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2729. Min Range: -7.2729
Max Act: 6.8354. Min Act: -0.1700
Data Index: 7890829 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2729. Min Range: -7.2729
Max Act: 6.8354. Min Act: -0.1700
Data Index: 6314628 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2729. Min Range: -7.2729
Max Act: 6.8667. Min Act: -0.1700
Data Index: 7916366 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2729. Min Range: -7.2729
Max Act: 6.8354. Min Act: -0.1700
Data Index: 4176308 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2729. Min Range: -7.2729
Max Act: 6.8354. Min Act: -0.1700
Data Index: 897877 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2729. Min Range: -7.2729
Max Act: 6.7729. Min Act: -0.1700
Data Index: 1225042 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2729. Min Range: -7.2729
Max Act: 6.8042. Min Act: -0.1700
Data Index: 5690079 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #19